Audiobook transcription, word by word. With chapters, captions and excerpts to promote it.
Audiobook transcription turns the recorded reading into text with every word timed, so you can proof it against the manuscript. Upload the recording files (MP3, WAV, M4A and more), one per chapter or the whole book. We return the text, chapters, SRT captions for the video version and MP3 excerpts to promote the book.
Updated
Why transcribe an audiobook. What weighs on production, and what gets lighter.
Hours of audio to proof
Proofing an audiobook by ear alone is slow and tiring. With the transcript, the proofer reads what was recorded next to the manuscript and flags where they differ: a skipped line, a swapped word, a name said another way. Search finds the line and shows exactly when it was said, so only that pickup gets re-recorded.
Knowing where each chapter starts
We generate chapters with titles and timestamps from what was read. When the narrator announces "Chapter twelve", a search for the word lands on every chapter start. On Studio and Agency, each chapter also lists its key moments, which helps when writing the blurb or picking the scene for a trailer.
Excerpts for launch promotion
On Studio and Agency, the hooks tab lists the book's strongest lines with an impact score, and every line carries the emotion it was read with: tension, tenderness, humor. Pick the passage, download it as an MP3 and post it with the cover. That is the sample that gets someone to listen to the rest.
A video version with captions
Posting chapter one on YouTube with a still cover on screen? Download SRT captions with the YouTube preset and import them into your editor, or FCPXML if you cut in Final Cut. If you filmed the narrator in the booth, upload that video: the same upload then also gives you vertical clips with burned-in captions.
A long book in many files
There is no length limit per file. Upload one file per chapter or the whole recording at once, and keep everything in a project named after the book. What counts is your plan's hours: a 7-hour book uses 7 hours. At a calm reading pace, narration runs at about 120 to 150 words per minute, so a 60,000-word novel comes to roughly 7 to 8 hours of audio.
Books read in other languages
Transcription works in 90+ languages, with automatic language detection. On Studio and Agency, captions can be translated into 9 languages, so the video version reaches readers abroad. The voice stays the original; what we translate is the captions.
How to transcribe an audiobook, from files to promo excerpts
- 01
Upload the recording
MP3, WAV, M4A, AAC, OGG or video, with no length limit. One file per chapter, or the whole book.
- 02
We transcribe and organize it
Text with every word timed, chapters, the emotion of each line and, on Studio and Agency, hooks with an impact score.
- 03
Proof it and promote it
A PDF of the text for proofing, SRT captions for the video version and MP3 excerpts for launch posts.
A 7-hour novel, from the booth to launch day
An independent narrator records a novel in 24 files, one per chapter. She creates a project named after the book and uploads them all. That is 7 hours of reading, which uses 7 hours of quota and fits Pro with room left in the month.
The proofer opens the transcript next to the manuscript and reads. In chapter 12, she notices a line of dialogue is missing. She searches the line before it, notes the timestamp and sends it to the narrator, who re-records only that pickup instead of the whole chapter.
For the launch, the narrator moves to Studio and opens the hooks tab. Among the top-scoring lines is the one about the Cape Cod postmark. She downloads three MP3 excerpts, one suspenseful, one funny and one tender, and posts each with the cover art.
Chapter one goes to YouTube as a free sample, with the cover on screen and the SRT captions imported in the editor. The timestamped chapters go in the description, and anyone who finds the sample gets a link to the full audiobook.
What you get from every audiobook transcript
| Output | Format | What it is for |
|---|---|---|
| Text of the reading | TXT or PDF | Proofing against the manuscript |
| Chapters | Timestamped list | Navigation and the sample's description |
| Captions | SRT with the YouTube preset, or FCPXML | Video version and accessibility |
| Excerpts | MP3 | Social promotion and samples |
| Hooks and emotions | Lines with an impact score (Studio and Agency) | Picking the strongest passages |
| Translated captions | 9 languages (Studio and Agency) | Samples for readers abroad |
“It went beyond my expectations. Creating emotions, hooks and scripts was a great experience.”
More than audiobook transcription. The same upload works for other long reads.
See also
A 7-hour book fits Pro. Two books a month call for Studio; a publisher with a full list, Agency.
Compare plans →- Transcription with speakers and chapters
- Emotions in every line
- Automatic clips with animated captions
- Remove pauses and filler words
- Downloads without watermark
See all features
- Manual clips, trimmed word by word
- Saved clip templates for the next ones
- Emotion filter
- Favorite and export lines in bulk
- Export as TXT, PDF, SRT, MP3 and MP4
- Everything in Pro
- Scored hooks and scripts
- Timeline for Premiere, DaVinci and Final Cut
- Translation and speaker names
- Your logo and your font on clips
- Connector for ChatGPT, Claude and Gemini
- Team: each person at R$ 29/month, with 3 more hours
See all features
- Moments inside each chapter
- Diagrams: mind map, flow and timeline
- Image and font library for clips
- Projects to organize by client
- Support
- Everything in Studio
- FilmScribe Plugin for DaVinci Resolve Studio (beta)
- Team with 2 people included
- Priority support
- Extra hours at R$ 7
3-day trial or 1 hour of material. See the result on your own recording before adding a card.
Frequently asked questions
How do I transcribe an audiobook to text?
Upload the recording files, one per chapter or the whole book, and we return the text with every word timed, chapters and the emotion of each line. Export it as TXT or PDF for proofing or to keep a text version of the reading.
Can I make captions for a video version?
Yes. Download SRT captions with the YouTube preset, or FCPXML for Final Cut, and import them into your editor with the cover art. If you filmed the reading, upload the video instead: you also get clips with burned-in captions.
Is there a length limit?
There is no length limit per file. What limits you is your plan's monthly hours: 10 on Pro, 20 on Studio, 35 on Agency. Past that, extra hours cost R$ 9, R$ 8 or R$ 7 depending on the plan.
Can I make promo clips from the audiobook?
From audio, excerpts come out as MP3, ready to post with the cover. On Studio and Agency, the hooks tab points you to the strongest lines. Video clips with burned-in captions and vertical framing need a video file, such as footage of the narrator in the booth.
How do I choose which passages to share?
Start with the hooks tab on Studio and Agency, which scores the strongest lines. On every plan, each line shows the emotion it was read with, and you can download any excerpt as an MP3. Pick short passages that work without context.
How much does audiobook transcription cost?
It depends on hours. A 7-hour book fits Pro at R$ 59 a month (10 hours). For two books a month, Studio has 20 hours for R$ 89. Agency has 35 hours for R$ 149. On annual billing, the monthly price is R$ 49, R$ 79 and R$ 139.